Google paper: Self-Improvement Memory lifts cross-model harness transfer from 68.41 to 84.75

rohanpaul_ai · x · 2026-11-18

A Google/Penn State paper introduces Continual Recursive Self-Improvement (CRSI) and Self-Improvement Memory (SIM) for agent harnesses — the code that runs prompts and tools.

Paper: arXiv:2611.18856, covering coding, text classification, workspace and engineering domains.

Related event: Google Proposes Self-Improvement Memory for Cross-Model Agent Harnesses(3 posts)→

Original post →

More from coding & agent

coding & agent channel →